{"as_of":"2026-08-08T09:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3855ed9dc1fe6b2340bc2d1e0ed0a4493b7bcef8f5cd9f5b24b0cb5ce2ac9e40","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:16:29.215085Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-20T10:18:11.872878Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.06700","last_updated":"2024-06-06T12:29:23Z","snapshot_observed_at":"2026-07-06T17:28:10.554625Z","submitted_at":"2024-02-09T07:45:26Z","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06700","snapshot_observed_at":"2026-08-07T11:16:29.215085Z","title":"arXiv:2402.06700","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05387","last_updated":"2025-06-11T16:08:29Z","snapshot_observed_at":"2026-08-08T01:16:04.570452Z","submitted_at":"2025-06-03T14:25:23Z","title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:29.215085Z"},"links":{"cited_paper":"/paper/2402.06700","citing_paper":"/paper/2506.05387"},"observation_digest":"sha256:4ad53e6d4a5ba3b578a6f570e389073c35bdcfb85f720ad26c3d233153b51b7c","observation_id":"f0f69048-4940-4a7c-8c9b-2503ce729b36","resolution":{"observed_at":"2026-08-07T11:16:29.215085Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06700","last_updated":"2024-06-06T12:29:23Z","snapshot_observed_at":"2026-07-06T17:28:10.554625Z","submitted_at":"2024-02-09T07:45:26Z","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06700","snapshot_observed_at":"2026-08-06T23:28:15.174905Z","title":"Entropy- regularized to ken-level policy optimization for language agent reinforcement,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21086","last_updated":"2025-06-22T15:36:27Z","snapshot_observed_at":"2026-08-06T23:20:49.214897Z","submitted_at":"2025-06-22T15:36:27Z","title":"Multi-Amateur Contrastive Decoding for Text Generation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:15.174905Z"},"links":{"cited_paper":"/paper/2402.06700","citing_paper":"/paper/2507.21086"},"observation_digest":"sha256:7bd9517ebafb8dc503cbf9ef287783e725643930c46086f5da4a7ce99a4def5c","observation_id":"bcf07401-23ed-448d-a23a-661e2eea50c4","resolution":{"observed_at":"2026-08-06T23:28:15.174905Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06700","last_updated":"2024-06-06T12:29:23Z","snapshot_observed_at":"2026-07-06T17:28:10.554625Z","submitted_at":"2024-02-09T07:45:26Z","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06700","snapshot_observed_at":"2026-08-03T10:01:25.614727Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.11960","last_updated":"2026-07-03T10:46:25Z","snapshot_observed_at":"2026-08-03T10:01:20.972258Z","submitted_at":"2026-01-17T08:30:50Z","title":"R$^2$PO: Decoupling Rollout and Inference Policies for LLM Reasoning","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-03T10:01:25.614727Z"},"links":{"cited_paper":"/paper/2402.06700","citing_paper":"/paper/2601.11960"},"observation_digest":"sha256:b0c0f63d81afa5346717c5f63682813539c8bf513990366ad0be816969577b4f","observation_id":"31b0c102-880e-4755-bbaa-8d84bca1bb8a","resolution":{"observed_at":"2026-08-03T10:01:25.614727Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06700","last_updated":"2024-06-06T12:29:23Z","snapshot_observed_at":"2026-07-06T17:28:10.554625Z","submitted_at":"2024-02-09T07:45:26Z","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","version":4},"cited_work":{"arxiv_id":"2402.06700","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.06700","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2402.06700 , year =","venue":null,"work_id":"942c8815-8794-4063-ae56-6e8c729e4d78","year":null},"citing_paper":{"arxiv_id":"2605.18191","last_updated":"2026-05-18T10:31:34Z","snapshot_observed_at":"2026-08-03T01:31:13.834606Z","submitted_at":"2026-05-18T10:31:34Z","title":"Pairwise Preference Reward and Group-Based Diversity Enhancement for Superior Open-Ended Generation","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-05-20T10:15:22.633882Z"},"links":{"cited_paper":"/paper/2402.06700","citing_paper":"/paper/2605.18191"},"observation_digest":"sha256:b315f25cbd0f21fcf9ed82fc0e2f0d6583310e21fe68f34f1524a3db00554cb6","observation_id":"0e5d7203-d1d9-4838-8800-dbbb6a3e972e","resolution":{"observed_at":"2026-05-20T10:18:11.875767Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.06700/citation-record","integrity":"/paper/2402.06700/integrity","json":"/paper/2402.06700/citation-record.json","paper":"/paper/2402.06700"},"outbound":[],"paper":{"arxiv_id":"2402.06700","last_updated":"2024-06-06T12:29:23Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T17:28:10.554625Z","submitted_at":"2024-02-09T07:45:26Z","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2402.06700."}